Reactive Combination of Belief Over Time Using Direct Perception

摘要

One issue for autonomous mobile robots operating in unknown, or partially known, domains is how to handle uncertainty in their sensor observations over time. Methods such as probabilistic belief networks and survivor functions are generally unsatisfactory because they require explicit models of the robot's interactions with its environment, including possible contravening events. This information is diffcult to obtain, and is philosophically incompatible with reactive behaviors.